© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11750
    Prev
    Next
    INDEX
    Explanations

    words related to various forms of abuse

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various forms of abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.79
     Camb
    -0.71
     Brah
    -0.68
     Kard
    -0.68
     Normandy
    -0.67
    vel
    -0.65
    ots
    -0.65
     floated
    -0.65
    Plan
    -0.65
    ç
    -0.64
    POSITIVE LOGITS
     abuse
    3.69
     Abuse
    2.78
    abuse
    2.75
     abused
    2.44
     abusers
    2.36
     abuses
    2.31
     abuser
    2.26
     abusing
    2.22
     misuse
    2.18
     abusive
    2.08
    Activations Density 0.025%

    No Known Activations